Pattern-recognition-based selection of optimal financial indicators for bankruptcy / delisting prediction
| Project/Area Number |
15K21395
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Library and information science/Humanistic social informatics
Management
|
|---|
| Research Institution | Tokyo University of Science |
|---|
Principal Investigator |
Hosaka Tadaaki 東京理科大学, 経営学部経営学科, 講師 (60516235)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
|---|
| Keywords | 倒産予知 / 実質破綻予知 / 機械学習 / AdaBoost / 深層学習 / 画像化 / 畳み込みニューラルネットワーク / 倒産早期予知 / 財務指標選択 / 実質破綻予測 |
|---|
| Outline of Final Research Achievements |
In this research, we aim to resolve some problems with respect to corporate bankruptcy prediction. We propose methods of 1) realizing the extraction of financial indicators and the derivation of discriminant functions in a consistent framework, and 2) applying the techniques of deep learning to bankruptcy prediction. As a result, we have shown that it is possible to predict with high accuracy even more than one year before bankruptcy. It was also shown that the method using deep learning can predict with high precision compared with the conventional methods.
|
Report
(4 results)
Research Products
(11 results)
